Count tokens for GPT-5, GPT-4o, Claude, and Gemini side-by-side. See input and output costs for every major model — tokenization runs in your browser, nothing is uploaded.
Characters
0
Words
0
GPT-4o / GPT-5 tokens
0
Claude tokens (approx)
0
| Model | Tokens | Input cost | Output cost |
|---|---|---|---|
| GPT-5 | 0 | $0.00 | $0.00 |
| GPT-5 Mini | 0 | $0.00 | $0.00 |
| GPT-5 Nano | 0 | $0.00 | $0.00 |
| GPT-4o | 0 | $0.00 | $0.00 |
| GPT-4.1 | 0 | $0.00 | $0.00 |
| GPT-4 Turbo | 0 | $0.00 | $0.00 |
| GPT-3.5 Turbo | 0 | $0.00 | $0.00 |
| Claude Opus 4.7* | 0 | $0.00 | $0.00 |
| Claude Sonnet 4.6* | 0 | $0.00 | $0.00 |
| Claude Haiku 4.5* | 0 | $0.00 | $0.00 |
| Gemini 2.5 Pro* | 0 | $0.00 | $0.00 |
| Gemini 2.5 Flash* | 0 | $0.00 | $0.00 |
* Claude and Gemini counts are approximations (~3.75 and ~4 chars/token). OpenAI counts are exact via tiktoken. Input cost assumes the full text is sent as a prompt; output cost would apply if the model returned text of the same length.
LLMs don't read characters or words — they read tokens, which are word fragments produced by a tokenizer. The tokenizer splits text using Byte-Pair Encoding (BPE): it starts with single characters and merges the most common pairs repeatedly until it has a vocabulary of ~50K-200K tokens. Common words like "the" become one token; rare words like "antidisestablishmentarianism" split into four or five.
Different model families use different tokenizers. OpenAI's o200k_base (GPT-4o, GPT-5 family) has a 200K vocabulary and is especially efficient for non-English text and emoji — roughly 15% fewer tokens than the older cl100k_base (GPT-4, GPT-3.5) for the same input. Anthropic's Claude uses a custom BPE that's similar to GPT but not publicly released — you can get exact counts via their /v1/messages/count_tokens API. Google's Gemini uses SentencePiece with a 256K vocabulary; their countTokens API returns exact counts.
Token count determines cost and context window usage. Cost is per-million tokens (input + output priced differently), so a 50K-token prompt to GPT-5 costs about $0.50 just to send — before counting the response. Context window is the total capacity per request; send more tokens than the window allows and the API returns an error. Knowing your count before you send avoids both cost surprises and error responses.
If you're building AI features, this tool pairs naturally with our System Prompt Generator: draft your prompt there, paste it here to check token count and cost before hardcoding it into production. Teams using Canary get automatic token accounting and cost visibility per conversation in the analytics dashboard.
Canary is an AI chatbot platform that trains on your website content, documentation, and FAQs to answer visitor questions 24/7. Unlike scripted chatbots, Canary uses a large language model with retrieval-augmented generation, so answers are grounded in your actual content — not generic AI guesses. Businesses use Canary to reduce support tickets by around 60%, capture leads after hours, and scale customer support without hiring.
Three ways, all in under 5 minutes: (1) paste your website URL and Canary crawls and indexes up to 500 pages, (2) upload PDFs, Word docs, Markdown, or CSVs directly, (3) add Q&A pairs manually for anything your docs don't cover. Canary automatically re-indexes whenever you add new content. You can combine multiple sources into one knowledge base.
About 5 minutes from signup to a live chatbot on your site. Point Canary at your website URL, wait for the crawl to complete (1-3 minutes for most sites), and paste one script tag into your HTML. The chatbot is trained on your content, styled to match your brand, and answering visitor questions with source citations — no code required beyond the single script tag.
Yes. Canary works on any HTML page — native support for WordPress, Shopify, Webflow, Squarespace, Wix, and any custom-built site. The widget is a single script tag (4KB, loads asynchronously, zero impact on page speed). React, Next.js, Vue, and Svelte apps also supported with the same one-line install.
Starter is free forever with 50 conversations/month. Growth is $49/month with 1,000 conversations, 5 knowledge sources, and team access. Scale is $149/month for unlimited conversations, unlimited knowledge sources, and priority support. Annual plans are discounted 20%. No per-message fees, no hidden costs, no credit card required for the free plan.
By default, GPT-5.4-nano — OpenAI's fastest current-generation model, tuned for customer support quality. You can switch per tenant to GPT-4o, GPT-5, or Claude models if you need more reasoning power, longer context, or multilingual strength. Model choice is a setting, not a plan gate — any paid plan can upgrade the model.
Yes. Canary's AI detects visitor intent — questions about pricing, integration, custom quotes — and asks for contact info in the natural flow of conversation, without forms. Captured leads sync to your email, CRM (HubSpot and Salesforce integrations built-in), or any tool via webhook. Lead capture is included in every plan, not an add-on.
Canary is trained to say "I don't know" rather than hallucinate — it only answers from your actual content. When it hits a knowledge gap, it offers to collect the visitor's email and hand the conversation off to a human via email notification, or passes the conversation directly into your support inbox. You control the escalation flow per tenant.
Yes. Canary auto-detects the visitor's language and responds in it — over 30 languages supported out of the box, including Spanish, French, German, Portuguese, Japanese, Arabic, and Hindi. Your source content can stay in English; Canary translates answers on the fly at response time. No additional configuration required.
Canary is multi-tenant with per-tenant vector store isolation — your content, conversations, and leads are never cross-queried with another tenant. Data is encrypted at rest and in transit. Visitor chat data is retained per your plan's retention policy (30 days on Starter, 90 days on Growth, unlimited on Scale). GDPR-compliant, with data-residency options available on Scale.
Join businesses that have automated support, captured more leads, and cut response times to zero — no code required.
Free forever on Starter. No credit card required.